NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV3C4HC0PP5JSW191DA68M
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.7s
Cost:
$0.011865
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
78.65%
Dialogue to Total Word Ratio
(details)
89.1996%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly spread the blueprints across the sticky diner table, smoothing out a smear of maple syrup with her sleeve. The layout of the Pemberton residence glowed under the flickering neon sign, every bouncy castle, piƱata, and present table marked in red ink like surgical targets. Bill hunched opposite her, stuffing hash browns into his mouth with the reverence of a man at communion. Crumbs tumbled onto the northwest entry point. "Watch the ketchup," she muttered. He grunted, wiping his mouth on a napkin already decorated with their getaway route. Seven-year-old Timmy Pemberton was turning eight on Saturday, and according to the RSVP list Molly had intercepted from the recycling bin, twenty-three children of venture capitalists and hedge fund managers would be in attendance. The gift table, by her calculations, would groan under at least forty thousand dollars of tastefully wrapped loot. Drones. Gold-plated Legos. A pony, possibly, though the pony presented logistical complications they hadn't yet resolved. Bill tapped the clown icon on the diagram, raising a greasy eyebrow. "You're the clown," Molly confirmed. He sighed, defeated, and reached for another pancake, already mourning the dignity he would surrender by Saturday afternoon at precisely two o'clock.
created_at
"2026-04-24T13:33:06.591Z"
4/24/2026, 1:33:06 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
923
moderation_latency
(null)
generation_time
7558
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
98
native_tokens_completion
455
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
usage
0.011865
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"95e7efe1-3f11-4f2d-9ab2-7225e845acc3"
is_byok
false
latency
923
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777037586-qGT3MGdEkerC0uqZY7V0"
session_id
(null)
api_type
"completions"
id
"gen-1777037586-neJfu2RluOJRxp1ntMNp"
upstream_id
"95e7efe1-3f11-4f2d-9ab2-7225e845acc3"
total_cost
0.011865
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
78.65%
Dialogue to Total Word Ratio
Ratio: 3.00%, Deviation: 7.00%
neededClean
false
wordsTotal
200
wordsDialogue
6
89.1996%